Arguments: AgentOptions
- TypeScript
- Python
string
required
Specifies the LLM provider.
Currently supporting:
- OpenAI:
openai - Anthropic:
anthropic
string
required
Specifies the LLM model.
Currently supporting:
- OpenAI:
computer-use-preview - Anthropic:
claude-sonnet-4-20250514andclaude-3-7-sonnet-latest
string
Specifies the system prompt
object
Configuration options for the LLM provider. Currently supports OpenAI and Anthropic SDK client options.
Returns: Promise<AgentResult>
boolean
If the agent execution completed without errors
string
Summary or error message from the agent
AgentAction[]
List of actions performed during execution
boolean
Whether the agent fully completed its task (can be false even if success is true)
Record<string, unknown> | dict
Optional additional data about the execution

